US6546114B1 - Technique for detecting a watermark in a marked image - Google Patents

Technique for detecting a watermark in a marked image Download PDF

Info

Publication number
US6546114B1
US6546114B1 US09/390,272 US39027299A US6546114B1 US 6546114 B1 US6546114 B1 US 6546114B1 US 39027299 A US39027299 A US 39027299A US 6546114 B1 US6546114 B1 US 6546114B1
Authority
US
United States
Prior art keywords
predefined
values
image
transform coefficients
sum
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
US09/390,272
Other languages
English (en)
Inventor
Ramarathnam Venkatesan
Mariusz Jakubowski
Thathachar S. Jayram
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Microsoft Technology Licensing LLC
Original Assignee
Microsoft Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Microsoft Corp filed Critical Microsoft Corp
Priority to US09/390,272 priority Critical patent/US6546114B1/en
Assigned to MICROSOFT CORPORATION reassignment MICROSOFT CORPORATION ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: THATHACHAR, JAYRAM S., JAKUBOWSKI, MARIUSZ, VENKATESAN, RAMARATHNAM
Priority to AU67871/00A priority patent/AU6787100A/en
Priority to PCT/US2000/022749 priority patent/WO2001018752A1/en
Application granted granted Critical
Publication of US6546114B1 publication Critical patent/US6546114B1/en
Assigned to MICROSOFT TECHNOLOGY LICENSING, LLC reassignment MICROSOFT TECHNOLOGY LICENSING, LLC ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: MICROSOFT CORPORATION
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G06T1/0021—Image watermarking
    • G06T1/005—Robust watermarking, e.g. average attack or collusion attack resistant
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
    • H04N1/32—Circuits or arrangements for control or supervision between transmitter and receiver or between image input and image output device, e.g. between a still-image camera and its memory or between a still-image camera and a printer device
    • H04N1/32101—Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title
    • H04N1/32144—Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title embedded in the image data, i.e. enclosed or integrated in the image, e.g. watermark, super-imposed logo or stamp
    • H04N1/32149—Methods relating to embedding, encoding, decoding, detection or retrieval operations
    • H04N1/32154—Transform domain methods
    • H04N1/3216—Transform domain methods using Fourier transforms
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
    • H04N1/32—Circuits or arrangements for control or supervision between transmitter and receiver or between image input and image output device, e.g. between a still-image camera and its memory or between a still-image camera and a printer device
    • H04N1/32101—Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title
    • H04N1/32144—Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title embedded in the image data, i.e. enclosed or integrated in the image, e.g. watermark, super-imposed logo or stamp
    • H04N1/32149—Methods relating to embedding, encoding, decoding, detection or retrieval operations
    • H04N1/32154—Transform domain methods
    • H04N1/32165—Transform domain methods using cosine transforms
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
    • H04N1/32—Circuits or arrangements for control or supervision between transmitter and receiver or between image input and image output device, e.g. between a still-image camera and its memory or between a still-image camera and a printer device
    • H04N1/32101—Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title
    • H04N1/32144—Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title embedded in the image data, i.e. enclosed or integrated in the image, e.g. watermark, super-imposed logo or stamp
    • H04N1/32149—Methods relating to embedding, encoding, decoding, detection or retrieval operations
    • H04N1/32154—Transform domain methods
    • H04N1/3217—Transform domain methods using wavelet transforms
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
    • H04N1/32—Circuits or arrangements for control or supervision between transmitter and receiver or between image input and image output device, e.g. between a still-image camera and its memory or between a still-image camera and a printer device
    • H04N1/32101—Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title
    • H04N1/32144—Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title embedded in the image data, i.e. enclosed or integrated in the image, e.g. watermark, super-imposed logo or stamp
    • H04N1/32149—Methods relating to embedding, encoding, decoding, detection or retrieval operations
    • H04N1/32154—Transform domain methods
    • H04N1/32187—Transform domain methods with selective or adaptive application of the additional information, e.g. in selected frequency coefficients
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2201/00—General purpose image data processing
    • G06T2201/005—Image watermarking
    • G06T2201/0052—Embedding of the watermark in the frequency domain
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2201/00—General purpose image data processing
    • G06T2201/005—Image watermarking
    • G06T2201/0065—Extraction of an embedded watermark; Reliable detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2201/00—General purpose image data processing
    • G06T2201/005—Image watermarking
    • G06T2201/0083—Image watermarking whereby only watermarked image required at decoder, e.g. source-based, blind, oblivious
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N2201/00—Indexing scheme relating to scanning, transmission or reproduction of documents or the like, and to details thereof
    • H04N2201/32—Circuits or arrangements for control or supervision between transmitter and receiver or between image input and image output device, e.g. between a still-image camera and its memory or between a still-image camera and a printer device
    • H04N2201/3201—Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title
    • H04N2201/3225—Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title of data relating to an image, a page or a document
    • H04N2201/3233—Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title of data relating to an image, a page or a document of authentication information, e.g. digital signature, watermark
    • H04N2201/3236—Details of authentication information generation

Definitions

  • the invention relates to image watermarking, particularly a technique, both apparatus and an accompanying method, for generating a highly secure cryptographic identifier, i.e., a watermark, for a non-marked image and embedding that watermark within the non-marked image itself in order to generate a “watermarked” image; for subsequently detecting that watermark in a test image; and the watermarked image so generated.
  • a highly secure cryptographic identifier i.e., a watermark
  • an image owner can readily, accurately and automatically determine whether the test image is a duplicate of the non-marked image.
  • a first technique utilizes an automatic approach.
  • an image owner utilizes a web crawler to successively visit one web site after another. For each site being visited, the crawler downloads corresponding image files for all images available at that site and compares each such file against stored data for each image owned by that person to detect whether any of the former images is a copy of any of the latter images, and if such a copy is found, provides appropriate notification to the image owner.
  • a relatively slight change to an image can defeat a finding of similarity between it and another image—even though to an human observer the two images are, visually speaking, very similar.
  • this technique being rather easy to frustrate, has proven to be inadequate.
  • a second technique relies on a manual approach. Simply stated, a human observer could visit a web site and examine each image provided by that site against a set of images to determine any matches between the two. A human observer could provide necessary interpretative skills to find image similarity where a comparison algorithm would not.
  • the number of sites accessible on the web is not only huge but also continues to exhibit exponential growth with no apparent decrease in its growth rate in sight.
  • the sheer magnitude of the manual task of just visiting each and every web site, let alone comparing images accessible through each such site renders this approach quite infeasible.
  • Another conventional technique that could be used relies on incorporating a watermark into an image and then detecting its presence in a suspected image copy.
  • pixel values that collectively form an image are transformed into another domain, i.e., a spatial frequency domain, to yield a set of transform coefficient values.
  • the watermark constitutes a set of pseudo-random perturbation values ( ⁇ ) (generated through use of a secret key “k”), wherein each of these values is heuristically selected and lies within a predefined range.
  • Each perturbation value is then added to its corresponding transform coefficient value to yield a “watermarked” image.
  • the pixel values in a test image i.e., a purported image copy
  • transform coefficients which are themselves then tested, using the perturbation values, to detect the presence of the watermark.
  • pixel values for an input image, I, to be watermarked are first transformed via, e.g., a DCT (discrete cosine transform), Fourier or wavelet transform, into the spatial frequency domain to yield transform coefficients.
  • the top N coefficients containing approximately 90% of the image power, i.e., M 1 , M 2 , . . . , M N are selected.
  • a secret “seed” value k a sequence of N pseudo-random perturbation values ⁇ 1 , ⁇ 2 , . . . , ⁇ N is generated.
  • That image is first transformed into a corresponding set of transform coefficients. Certain coefficients are then selected in the same manner set forth above to yield selected coefficients. The selected coefficients are then tested through a single mathematical test, in conjunction with the perturbation values that might have been used to mark the image, so as to detect the presence of these perturbation values, ⁇ , in the suspected copy.
  • such a technique should provide a highly secure identifier, such as a watermark, for an image where the identifier could be embedded within the image itself and would be extremely difficult, if not effectively impossible, to remove or frustrate.
  • detecting whether an supposed replica is a copy of an image could occur by merely detecting whether the replica contains the particular watermark associated with the image or not. If the replica were to contain that watermark, then upon consulting a database of authorized users, an image owner could conclusively determine whether the replica is an authorized or illicit (i.e., “pirated”) copy.
  • such a technique would be particularly amenable to being automatically implemented, such as in a PC or workstation, thereby obviating a need for laborious manual image comparisons.
  • Our present invention advantageously satisfies this need by creating a highly secure watermark for an original (in the sense of being an “input”) image, by transforming data, i.e., pixel values and specifically pixel intensity values, for-that image into a series of transform coefficients; adding corresponding, though relatively small, but specifically determined pseudo-random perturbations to these coefficients, wherein all-the perturbations collectively satisfy a plurality of mathematical constraints; and then creating a “watermarked” version of this image by applying a reverse transformation on the perturbed coefficients to yield resulting image data.
  • the resulting image data rather than original image data, is then used whenever that image is to be publicly disseminated, whether by distribution through a web server, by diskette or by any other insecure distributional vehicle.
  • the watermark while being basically imperceptible to a viewer, is essentially, if not totally, impossible to remove from the image (i.e., for all intents and purposes, is “indelible”) and hence is highly secure against tampering by a third party.
  • any subsequent replica of the watermarked image will itself also contain the watermark.
  • these replicas can be automatically detected, without a need for human intervention, by simply analyzing whether a given (“test”) image contains the watermark (i.e., it is an image replica) or not.
  • the perturbation values are specifically chosen not to collectively satisfy just one mathematical constraint, but rather a plurality of different such constraints.
  • the individual perturbation values, ⁇ i are preferably kept relatively small, e.g., ⁇ 1 for processing simplicity, to render essentially imperceptible any visually apparent artifacts in the watermarked image that might otherwise arise from use of larger perturbation values.
  • each transform coefficient M i in the image to be watermarked is perturbed by a specific predefined amount to define a gross perturbation which constitutes the watermark.
  • test image i.e., test image, I′
  • that image is first transformed into a corresponding set of transform coefficients. Selected coefficients are then collectively tested by utilizing a series of different mathematical tests, on different corresponding subsets of these selected coefficients, to detect whether at least a majority of the perturbation values are present in the test image.
  • the perturbation values, for each of the K subsets of the random integer values for the test image and associated with the watermark, are separately tested to determine whether a majority of the subsets of the pseudo-random perturbation values collectively exist in the test image.
  • an expression Q i ⁇ j ⁇ S i ⁇ ⁇ ⁇ j ⁇ ⁇ r j
  • the difficulty of effectively jamming the watermark significantly increases, as hence the security provided by the watermark, as the number (K) of subsets increases.
  • This number can be set to a value that imparts a desired level of security to the watermark consistent with computational resources then available to process each test image in order to detect the watermark.
  • FIG. 1 depicts a high-level block diagram of a manner through which image files are commonly and conventionally duplicated, on an unauthorized basis, for use with third party web sites, i.e., “image piracy”;
  • FIG. 2 depicts a simplified high-level block diagram of conventional watermarking process 200 ;
  • FIG. 3 depicts a high-level block diagram of process 300 for marking an image
  • FIG. 4A depicts a high-level block diagram of well-known watermark recovery process 400 for recovering a conventional watermark from an image
  • FIG. 4B depicts a high-level block diagram of our inventive process 450 for recovering an enhanced watermark from a image
  • FIG. 5 depicts a high-level block diagram of computer system 500 , illustratively a personal computer (PC), that can be used to implement our present invention
  • PC personal computer
  • FIG. 6 depicts a high-level block diagram of application programs 600 shown in FIG. 5;
  • FIG. 7 depicts a flowchart of image marking procedure 700 that is executed within application programs 600 shown in FIG. 6;
  • FIG. 8 depicts a flowchart of enhanced watermark generation procedure 800 that is executed by procedure 700 shown in FIG. 7 to generate an enhanced watermark
  • FIG. 9 depicts a flowchart of enhanced watermark recovery procedure 900 for recovering, from a test image, an enhanced watermark generated through use of procedure 800 shown in FIG. 8 .
  • This collection can be any sizeable dataset, such as an image, a database or the like, where, given the nature of the data itself, an embedded identifier, collectively formed of relatively small perturbations in a transformed data space, will only have minimal, if any, adverse affect on the ultimate processing and/or, e.g., in the case of an image, the display of that image.
  • an embedded identifier collectively formed of relatively small perturbations in a transformed data space
  • FIG. 1 Such piracy is depicted, in elementary form, in FIG. 1 .
  • a web site owner creates, as symbolized by block 10 , an original image which yields digital image file 15 .
  • the owner then links this file to web pages 25 and posts the file for the pages and the image to web server 20 for subsequent public access through, e.g., Internet 50 .
  • a remote third party by executing web browser 62 , at client PC 60 , may establish a connection through Internet 50 to server 20 and download web pages 25 , including image file 15 , to form downloaded page files 64 .
  • the third party likes the image embodied by image file 15 , that party may simply locally save the image file, as replica image file 15 ′, apart from the web page files.
  • that party may simply, as symbolized by line 75 , incorporate that replica image file into his(her) own web pages and hence transfer the replica image file to his(her) web server 80 , from which other individuals could access that same image, and so forth.
  • other third parties as symbolized by lines 70 , could directly access web server 20 and download image file 15 and, in turn, distribute replicas of the image.
  • a watermark is simply an insignia produced by a permanent local variation in a physical or chemical characteristic(s), e.g., structure or opacity, of the document.
  • the watermark remains invisible to, e.g., a human eye, unless the document is subjected to a predefined watermark recovery process, such as holding the document at a particular angle to a light source, subjecting the document to light of a predefined wavelength (such as ultraviolet), or, in the case of a true watermark, wetting the document with water.
  • a predefined watermark recovery process such as holding the document at a particular angle to a light source, subjecting the document to light of a predefined wavelength (such as ultraviolet), or, in the case of a true watermark, wetting the document with water.
  • the specific process needed to reveal the watermark is governed by the manner through which the watermark altered the underlying characteristic(s) of the document itself.
  • the presence of the watermark signifies to the holder of the document that the document, if no copies have been legally made, is an original, or if present on a known copy, authenticates that copy as being legitimate.
  • FIG. 2 depicts a simplified high-level block diagram of conventional watermarking process 200 .
  • an object, O to be protected, whether it be a printed image, a document, a piece of paper currency or some other such item, is applied, as symbolized by line 205 , to marking process 210 situated at an originating location.
  • marking process 210 situated at an originating location.
  • This process creates a watermark and embeds it in the object to create a watermarked object, O′.
  • the watermarked object is then eventually transported through insecure channel 215 , whether it be, e.g., transit through a public carrier or, as in the case of currency, public distribution, to a destination location.
  • the watermarked object is subjected to watermark recovery process 230 which attempts to recover the watermark from the object and, based on a result of the recovery process, indicates, as symbolized by output line 235 , whether the watermark is present or not in object O′.
  • This indication can be used to signify whether watermark object O′, then situated,as symbolized by line 220 , at the destination is legitimate or not. Since the legitimacy of the document is directly governed by the security of the watermark, the watermark itself must be as difficult as possible for a third party to copy or alter.
  • the highly secure watermark is created for an original image, by transforming data for that image, i.e., pixel values and specifically pixel intensity values, into a series of transform coefficients; adding corresponding, though relatively small, but specifically determined pseudo-random perturbation values, that satisfy a plurality of mathematical constraints, to these coefficients; and then creating a watermarked version of this image by applying a reverse transformation on the perturbed coefficients to yield resulting image data.
  • the resulting image data rather than original image data, is then used whenever that image is to be publicly disseminated, whether by distribution through a web server, by diskette or by any other insecure distributional vehicle.
  • the watermark while being basically imperceptible to a viewer, is essentially, if not totally, impossible to remove from the image (i.e., for all intents and purposes, is “indelible”) and hence is highly secure against tampering by a third party.
  • any subsequent replica of the watermarked image will itself also contain the watermark.
  • these replicas can be automatically detected, without a need for human intervention, by simply analyzing whether an image “under test” contains the watermark (i.e., it is an image replica) or not.
  • FIGS. 3, 4 A and 4 B depict high-level block diagrams of image marking and watermark recovery processes.
  • FIG. 3 depicts process 300 for forming a watermark for an image. As generally shown, this process is common, though with specific differences as discussed below, to both.the conventional and our present inventive approaches.
  • pixel values m 1 , m 2 , . . . , m n (where n is an integer representing a total number of pixel values), that collectively form an input image, I, are applied, as symbolized by lead 305 , to transform operation 310 .
  • These pixel values can represent values for any color space of interest, e.g., a value for a single range (chrominance) of coloration or a value for a hue of a red, green, blue (RGB) color or other color of interest in that space.
  • RGB red, green, blue
  • the transform operation which is typified by a Fourier, discrete cosine (DCT) or wavelet transform, transforms the pixel values into another domain, i.e., here a spatial frequency domain, to yield a set of transform coefficient value's.
  • DCT discrete cosine
  • the specific transform used is also not critical provided the same transform, though in inverse directions, is used to generate and recover the watermark.
  • the transform used need not be one that transforms the pixel values to the frequency domain; transforms that utilize other domains could be used—again provided these transforms are consistently used for both creating and recovering the watermark.
  • the inventive embodiments will illustratively employ a frequency transformation.
  • the resulting transform coefficient values, produced by operation 310 are applied to coefficient selection process 320 which selects in accordance with a predefined selection metric certain desired ones (M 1 , M 2 , . . . , M N ) of these coefficients.
  • a predefined selection metric chooses a random subset of a set of N coefficients in the 90 th percentile of power in the image; the other coefficients are simply discarded.
  • Other predefined selection metrics can be used provided that this metric is consistently applied both in marking an image and in recovering the watermark from it (particularly a suspected replica of it).
  • those coefficients, M 1 , M 2 , . . . , M N are applied, as symbolized by lead 325 , to one input of vector summing operation 340 .
  • the other input to this summing operation, as symbolized by lead 335 is a set of relatively small pseudo-random perturbation values, which collectively constitute the watermark.
  • These perturbation values are produced by watermark creation process 330 . This process generates these perturbation values in response to a secret seed value “k” (where k is a predefined integer and, as a secret value, not publicly known) and a predefined value ⁇ F .
  • the perturbation values, ⁇ i are kept relatively small, e.g., ⁇ 1 for processing simplicity, to render essentially imperceptible any visually apparent artifacts in a resulting watermarked image that might otherwise arise from use of larger perturbations.
  • a sequence of N pseudo-pseudo-random secret coefficients ⁇ i , ⁇ 2 , . . . , ⁇ N is generated using the secret value “k” as a seed, where all these coefficients collectively satisfy a single mathematical constraint, as given by equations (1) and (2) below: [ ⁇ i N ⁇ ⁇ i / N ] ⁇ ⁇ F ( 1 ) ⁇ i N ⁇ ⁇ i 2 ⁇ ⁇ F ( 2 )
  • ⁇ F and ⁇ F are both empirically defined constants.
  • each perturbation value, ⁇ i is preferably ⁇ 1, this value is not so limited and in fact can be any numerical value that satisfies equation (1) above.
  • K random subsets (S 1 , S 2 , . . . , S K ) of integers (S) (S j ⁇ R ⁇ 1,2, . . . , N ⁇ ) are first selected. Rather than being randomly picked, the value of K can be chosen to impart a desired level of security to the watermark consistent with computational resources then available to subsequently detect the watermark in each test image.
  • each of the subsets (S i ) designates members of a subset of perturbation values ( ⁇ j ) and transform coefficients (M j ).
  • the perturbation values used in our inventive approach collectively satisfy not just one constraint, as conventionally occurs, but rather a plurality of different mathematical constraints.
  • each resulting perturbation value ⁇ i is then added to a corresponding selected transform coefficient value, m i , to yield a “watermarked” image in the transform domain, such that M 1 ⁇ M 1 + ⁇ 1 , M 2 ⁇ M 2 + ⁇ 2 and so on.
  • Resulting perturbed transformed coefficients are then applied, as symbolized by lead 345 , to inverse transformation operation 350 which, in turn, transforms the watermarked image back to its original (optical) domain.
  • Operation 350 is the inverse of the transform used in operation 310 .
  • the “marked” pixel values for the resulting watermarked image collectively appear as output, as symbolized by lead 355 .
  • FIGS. 4A and 4B We will now turn to our discussion of conventional and inventive recovery processes shown in FIGS. 4A and 4B. To simplify reader understanding, the reader should also simultaneously refer to FIG. 3 throughout the following discussion of FIGS. 4A and 4B.
  • FIG. 4A generally depicts conventional process 400 for recovering a non-enhanced watermark from a test image.
  • the assumption, subject to confirmation by process 400 is that the test image contains a non-enhanced watermark created through process 300 (shown in FIG. 3 ).
  • I′ To detect such a watermark in the test image, I′, pixel values (m 1 ′, m 2 ′, . . . , m n ′) for that image are first transformed, through transform operation 410 , into a corresponding set of transform coefficients. This operation is identical to transform operation 310 used to mark the image.
  • r i is the i th received transform coefficient
  • a resulting value for Q is compared, via operation 440 , against a predefined threshold value, T. If the value of Q exceeds the threshold value, then operation 440 produces an output, as symbolized by line 443 , signifying that the watermark is present in the test image. Otherwise, operation 440 produces an output, as symbolized by line 447 , signifying that the watermark is not present in the test image.
  • FIG. 4B generally depicts our inventive process 450 for recovering an enhanced watermark from a test image.
  • the assumption, subject to confirmation by process 450 is that the test image contains an enhanced watermark created through process 300 (shown in FIG. 3 ).
  • operation 320 in the same manner as does operation 320 .
  • a probabilistic selection procedure e.g., based on sorting by numerical values and thresholding
  • the selected coefficients are then tested by amplified test operation 480 .
  • operation 484 calculates a sum-product for a corresponding subset of the perturbation values, and corresponding transform coefficients, according to equation (4) as follows:
  • Q i ⁇ for ⁇ ⁇ all j ⁇ S i ⁇ ⁇ ⁇ j ⁇ ⁇ r j ( 4 )
  • r j is the j th received transform coefficient
  • test operation 486 determines if each one of a majority of the Q i values exceeds the predefined threshold, T. If so, then the test image contains the enhanced watermark, and, as symbolized by line 492 , operation 486 produces an appropriate indication. In this case, test image I′ is viewed as a copy (replica) of original image I. Otherwise, operation 486 concludes that the test image does not contain the enhanced watermark and produces an appropriate indication as symbolized by line 494 . Alternatively, operation 486 may implement an “amplified” approach rather than a threshold based test.
  • FIG. 5 depicts a block diagram of personal computer (PC) 500 on which our present invention can be implemented.
  • FIGS. 6-11 depict the salient software.
  • client computer 500 comprises input interfaces (I/F) 520 , processor 540 , communications interface 550 , memory 530 and output interfaces 560 , all conventionally interconnected by bus 570 .
  • Memory 530 which generally includes different modalities, including illustratively random access memory (RAM) 532 for temporary data and instruction store, diskette drive(s) 534 for exchanging information, as per user command, with floppy diskettes, and non-volatile mass store 535 that is implemented through a hard disk, typically magnetic in nature.
  • Mass store 535 may also contain a CD-ROM or other optical media reader (not specifically shown) (or writer) to read information from (and write information onto) suitable optical storage media.
  • the mass store stores operating system (O/S) 537 and application programs 600 ; the latter illustratively containing marking and recovery programs 630 and 700 (see FIG. 6) which incorporate our inventive techniques O/S 537 , shown in FIG. 5, may be implemented by any conventional operating system, such as the WINDOWS NT operating system (“WINDOWS NT” is a registered trademark of Microsoft Corporation of Redmond, Wash.). Given that, we will not discuss any components of O/S 537 as they are all irrelevant. Suffice it to say, that application programs 600 execute under control of the O/S.
  • O/S operating system
  • application programs 600 execute under control of the O/S.
  • Incoming information can arise from two illustrative external sources: network supplied information, e.g., from the Internet and/or other networked facility, through network connection 555 to communications interface 550 , or from a dedicated input source, via path(es) 510 , to input interfaces 520 .
  • Dedicated input can originate from a wide variety of sources, e.g., a scanner, a dedicated link or an external database.
  • input information can also be provided by inserting a diskette containing an input image file(s) into diskette drive 534 from which computer 500 , under user instruction, will access and read that file(s) from the diskette.
  • Input interfaces 520 contain appropriate circuitry to provide necessary and corresponding electrical connections required to physically connect and interface each differing dedicated source of input information to computer system 500 .
  • application programs 600 exchange commands and data with the external sources, via network connection 555 or path(es) 510 , to transmit and receive information typically requested by a user during program execution.
  • Input interfaces 520 also electrically connect and interface user input device 595 , such as a keyboard and mouse, to computer system 500 .
  • Display 580 such as a conventional color monitor, and printer 585 , such as a conventional laser printer, are connected, via leads 563 and 567 , respectively, to output interfaces 560 .
  • the output interfaces provide requisite circuitry to electrically connect and interface the display and printer to the computer system.
  • our present inventive image watermarking technique can operate with any type of digital image information regardless of the modalities through which client computer 500 will obtain, store and/or communicate that information.
  • FIG. 6 depicts a high-level block diagram of application programs 600 that execute on PC 500 (see FIG. 5 ). As shown in FIG. 6, these programs contain web crawler 610 , enhanced watermark recovery procedure 900 and image marking procedure 700 .
  • web crawler 610 automatically and conventionally “crawls” the web, interrogating one web site after another, and downloading, via input 605 , all web pages available at each site it visits. These pages are processed, within the web crawler, through image file extraction process 615 which extracts each image file (generally based on its file type as encoded in its file name suffix—e.g., *.JPEG, *.GIF and so forth) associated with every downloaded page. These image files are then routed, in succession, as test images, I′, to enhanced watermark recovery procedure 900 . Test images are also directly applied, as symbolized by input 625 , to procedure 900 , such as through connection 510 for a dedicated input source.
  • image file extraction process 615 which extracts each image file (generally based on its file type as encoded in its file name suffix—e.g., *.JPEG, *.GIF and so forth) associated with every downloaded page.
  • image files are then routed, in succession, as test images, I′,
  • Procedure 900 determines whether each test image contains either an enhanced watermark and hence is a copy of a watermarked image generated through procedure 700 .
  • Procedure 900 provides an appropriate output indication as to the presence/absence of a watermark, on output 635 , which can be used in subsequent processing such subsequent processing may involve interrogating an appropriate database (not shown) with an address (e.g., a uniform resource locator—URL) of the web site from which the image was downloaded and an indication of the presence/absence of the watermark to determine whether that image is a licensed copy for which a royalty has been paid or not and thus generate an appropriate response, such as, e.g., debiting an account with a predetermined royalty charge for that particular copy.
  • an address e.g., a uniform resource locator—URL
  • Image marking procedure 700 watermarks an input image, I as symbolized by input 645 , in the manner discussed above in conjunction with procedure 300 (shown in FIG. 3) with, as desired, an enhanced watermark to generate, as symbolized by output 655 , a marked image.
  • FIG. 7 depicts a flowchart of image marking procedure 700 that is executed within application programs 600 shown in FIG. 6 .
  • execution Upon entry into procedure 700 , execution first proceeds to block 710 .
  • This block executes procedure 800 to generate secret pseudo-random perturbation values, ⁇ , for an enhanced watermark.
  • the individual perturbation values, ⁇ i , provided by procedure 800 are preferably kept relatively small, e.g., ⁇ 1 for processing simplicity, to render essentially imperceptible any visually apparent artifacts in the watermarked image that might otherwise arise from use of larger perturbations.
  • block 750 executes to update each selected transform coefficient by its corresponding perturbation value as per equation (5) as follows:
  • execution proceeds to block 760 which processes the updated transform coefficients through an inverse transformation, F ⁇ 1 , to yield optical domain (e.g., chrominance) data for the watermarked image. Thereafter, execution exits from procedure 700 .
  • F ⁇ 1 an inverse transformation
  • FIG. 8 depicts a flowchart of enhanced watermark generation procedure 800 that can be executed by procedure 700 (see FIG. 7) for generating the secret pseudo-random perturbation values for an enhanced watermark.
  • execution upon entry into procedure 800 , execution first proceeds to block 810 which reads, from input data, secret value k and value N. Next, execution proceeds to block 820 which randomly selects an integer, K, within a set of integer values 1 to N inclusive. Thereafter, block 830 executes to determine K different subsets ⁇ S 1 , S 2 , . . . , S K ⁇ of randomly selected integers, where each of the integers is a real value in the range of 1 to N inclusive. The number of integers contained in each of the subsets is also a integer value randomly selected between 1 to N inclusive. Once all these subsets have been determined, these subsets are saved for use in subsequently recovering the enhanced watermark from a test image(s).
  • each of the K subsets (S i ) designates members of a subset of perturbation values ( ⁇ j ) and transform coefficients (M j ).
  • block 840 can utilize any one of a wide variety of conventional optimization algorithms well known in the art to determine each perturbation value, ⁇ i .
  • each constraint could sum to a predefined non-zero value ⁇ i .
  • these predefined non-zero values would also be read by procedure 810 as input data. If such non-zero values were to be used, then, during watermark recovery, an appropriate and different threshold value would need to be used with each such subset of perturbation values.
  • FIG. 9 depicts a flowchart of enhanced watermark recovery procedure 900 for recovering, from a test image, an enhanced watermark generated through use of procedure 800 shown in FIG. 8 .
  • execution Upon entry into procedure 900 , execution first proceeds to block 905 to read pixel values for a test image, I′. Once these values have been read, execution proceeds to block 907 which performs a conventional contrast-enhancement operation on the image. Thereafter, a resulting enhanced test image is applied to block 910 .
  • block 925 when executed, accesses every perturbation value ( ⁇ j ) previously used to form the watermark in the test image and specified by a different member of the i th subset of random integer values (S) used in marking that image, forms a product of each such perturbation value and its corresponding received transform coefficient (r i ), and forms a sum of the products, as given by equation (3) above.
  • S random integer values
  • r i received transform coefficient
  • decision block 930 routes execution, via NO path 934 , to block 940 .
  • This latter block increments the value of counter i by one.
  • execution loops back, via feedback path 945 , to block 925 to compute the sum-product for the next subset of perturbation values, and so forth.
  • decision block 930 routes execution, via YES path 937 , to decision block 950 .
  • This latter decision block determines whether each one of the sum-products, for a majority of the subsets (Q i ) of the perturbation values present in the test image, exceeds a predefined threshold value, T. If so, then the test image contains the enhanced watermark.
  • decision block 950 routes execution, via YES path 957 , to block 965 .
  • This latter block produces an appropriate output to signify the existence of the enhanced watermark in the test image.
  • test image I′ is viewed as a copy of original image I.
  • decision block 950 routes execution, via NO path 953 , to block 960 .
  • block 960 produces an output that signifies that the test image does not contain the enhanced watermark.
  • execution exits, via path 970 , from routine 900 .
  • block 950 implements an “amplified” approach rather than a threshold based test.
US09/390,272 1999-09-07 1999-09-07 Technique for detecting a watermark in a marked image Expired - Fee Related US6546114B1 (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US09/390,272 US6546114B1 (en) 1999-09-07 1999-09-07 Technique for detecting a watermark in a marked image
AU67871/00A AU6787100A (en) 1999-09-07 2000-08-18 A technique for watermarking an image and a resulting "watermarked" image
PCT/US2000/022749 WO2001018752A1 (en) 1999-09-07 2000-08-18 A technique for watermarking an image and a resulting 'watermarked' image

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US09/390,272 US6546114B1 (en) 1999-09-07 1999-09-07 Technique for detecting a watermark in a marked image

Publications (1)

Publication Number Publication Date
US6546114B1 true US6546114B1 (en) 2003-04-08

Family

ID=23541808

Family Applications (1)

Application Number Title Priority Date Filing Date
US09/390,272 Expired - Fee Related US6546114B1 (en) 1999-09-07 1999-09-07 Technique for detecting a watermark in a marked image

Country Status (1)

Country Link
US (1) US6546114B1 (US06546114-20030408-M00003.png)

Cited By (41)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020172394A1 (en) * 2001-04-24 2002-11-21 Ramarathnam Venkatesan Robust and stealthy video watermarking
US20020172425A1 (en) * 2001-04-24 2002-11-21 Ramarathnam Venkatesan Recognizer of text-based work
US20020183967A1 (en) * 2001-04-12 2002-12-05 Koninklijke Philips Electronics N.V. Methods and apparatus for verifying the presence of original data in content while copying an identifiable subset thereof
US20020199107A1 (en) * 2001-04-12 2002-12-26 Koninklijke Philips Electronics N.V. Methods and appararus for verifying the presence of original data in content
US20030009670A1 (en) * 2001-04-02 2003-01-09 Digimarc Corporation Background watermark processing
US20030165253A1 (en) * 2002-03-01 2003-09-04 Simpson Shell Sterling Systems and methods for adding watermarks using network-based imaging techniques
US20040001626A1 (en) * 2002-01-11 2004-01-01 Severine Baudry Method and system to decode image watermarks
US20040001605A1 (en) * 2002-06-28 2004-01-01 Ramarathnam Venkatesan Watermarking via quantization of statistics of overlapping regions
US20040013285A1 (en) * 2000-09-20 2004-01-22 Frederic Jordan Method for preventing counterfeiting or alteration of a prited or engraved surface
US20040025025A1 (en) * 1999-10-19 2004-02-05 Ramarathnam Venkatesan System and method for hashing digital images
US6768809B2 (en) 2000-02-14 2004-07-27 Digimarc Corporation Digital watermark screening and detection strategies
US20040210539A1 (en) * 2003-04-21 2004-10-21 Yamaha Corporation Music-content using apparatus capable of managing copying of music content, and program therefor
US20050022004A1 (en) * 2001-04-24 2005-01-27 Microsoft Corporation Robust recognizer of perceptually similar content
US20050066177A1 (en) * 2001-04-24 2005-03-24 Microsoft Corporation Content-recognition facilitator
US20050108543A1 (en) * 2001-04-24 2005-05-19 Microsoft Corporation Derivation and quantization of robust non-local characteristics for blind watermarking
US20050125358A1 (en) * 2003-12-04 2005-06-09 Black Duck Software, Inc. Authenticating licenses for legally-protectable content based on license profiles and content identifiers
US20050125359A1 (en) * 2003-12-04 2005-06-09 Black Duck Software, Inc. Resolving license dependencies for aggregations of legally-protectable content
US20050149727A1 (en) * 2004-01-06 2005-07-07 Kozat S. S. Digital goods representation based upon matrix invariances
US20050165690A1 (en) * 2004-01-23 2005-07-28 Microsoft Corporation Watermarking via quantization of rational statistics of regions
US20050175224A1 (en) * 2004-02-11 2005-08-11 Microsoft Corporation Desynchronized fingerprinting method and system for digital multimedia data
US20060116966A1 (en) * 2003-12-04 2006-06-01 Pedersen Palle M Methods and systems for verifying protectable content
WO2006065023A1 (en) * 2004-12-13 2006-06-22 Electronics And Telecommunications Research Institute Method and systems for selecting test stimuli for use in evaluating performance of video watermarking methods
US20060167813A1 (en) * 2003-02-25 2006-07-27 Ali Aydar Managing digital media rights through missing masters lists
US20060167882A1 (en) * 2003-02-25 2006-07-27 Ali Aydar Digital rights management system architecture
US20060167807A1 (en) * 2003-02-25 2006-07-27 Ali Aydar Dispute resolution in an open copyright database
US20060167804A1 (en) * 2003-02-25 2006-07-27 Ali Aydar Track listening and playing service for digital media files
US20060167803A1 (en) * 2003-02-25 2006-07-27 Ali Aydar Batch loading and self-registration of digital media files
US20060212403A1 (en) * 2003-02-25 2006-09-21 Shawn Fanning Method of processing song claims involving songs including, but not limited to musical works, compositions, etc.
US20060212464A1 (en) * 2005-03-18 2006-09-21 Pedersen Palle M Methods and systems for identifying an area of interest in protectable content
US7136535B2 (en) 2002-06-28 2006-11-14 Microsoft Corporation Content recognizer via probabilistic mirror distribution
US20070260651A1 (en) * 2006-05-08 2007-11-08 Pedersen Palle M Methods and systems for reporting regions of interest in content files
US20070297014A1 (en) * 2006-06-23 2007-12-27 Takeshi Kuga Image processing system and image processing method
US20080091938A1 (en) * 2006-10-12 2008-04-17 Black Duck Software, Inc. Software algorithm identification
US20080091677A1 (en) * 2006-10-12 2008-04-17 Black Duck Software, Inc. Software export compliance
US20080154965A1 (en) * 2003-12-04 2008-06-26 Pedersen Palle M Methods and systems for managing software development
US7770014B2 (en) 2004-04-30 2010-08-03 Microsoft Corporation Randomized signal transforms and their applications
US20110238664A1 (en) * 2010-03-26 2011-09-29 Pedersen Palle M Region Based Information Retrieval System
US20140130148A1 (en) * 2012-11-02 2014-05-08 Sony Corporation Information processing device, information processing method, and computer program
WO2015099646A1 (en) * 2013-12-23 2015-07-02 Thomson Licensing Method and system for matching images and display devices
US10182170B1 (en) 2016-02-03 2019-01-15 Digimarc Corporation Methods and arrangements for adaptation of barcode reading camera systems for digital watermark decoding
EP4124991A1 (de) * 2021-07-30 2023-02-01 Sick Ag Verfahren zum automatischen einrichten einer codelesevorrichtung und kamerabasierte codelesevorrichtung

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5875249A (en) * 1997-01-08 1999-02-23 International Business Machines Corporation Invisible image watermark for image verification
US5960081A (en) * 1997-06-05 1999-09-28 Cray Research, Inc. Embedding a digital signature in a video sequence
US6094483A (en) * 1997-08-06 2000-07-25 Research Foundation Of State University Of New York Secure encryption and hiding of data and messages in images

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5875249A (en) * 1997-01-08 1999-02-23 International Business Machines Corporation Invisible image watermark for image verification
US5960081A (en) * 1997-06-05 1999-09-28 Cray Research, Inc. Embedding a digital signature in a video sequence
US6094483A (en) * 1997-08-06 2000-07-25 Research Foundation Of State University Of New York Secure encryption and hiding of data and messages in images

Cited By (94)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7421128B2 (en) 1999-10-19 2008-09-02 Microsoft Corporation System and method for hashing digital images
US20040025025A1 (en) * 1999-10-19 2004-02-05 Ramarathnam Venkatesan System and method for hashing digital images
US6768809B2 (en) 2000-02-14 2004-07-27 Digimarc Corporation Digital watermark screening and detection strategies
US20040013285A1 (en) * 2000-09-20 2004-01-22 Frederic Jordan Method for preventing counterfeiting or alteration of a prited or engraved surface
US7684088B2 (en) * 2000-09-20 2010-03-23 Alpvision S.A. Method for preventing counterfeiting or alteration of a printed or engraved surface
US20030009670A1 (en) * 2001-04-02 2003-01-09 Digimarc Corporation Background watermark processing
US20020183967A1 (en) * 2001-04-12 2002-12-05 Koninklijke Philips Electronics N.V. Methods and apparatus for verifying the presence of original data in content while copying an identifiable subset thereof
US20020199107A1 (en) * 2001-04-12 2002-12-26 Koninklijke Philips Electronics N.V. Methods and appararus for verifying the presence of original data in content
US7406195B2 (en) 2001-04-24 2008-07-29 Microsoft Corporation Robust recognizer of perceptually similar content
US20020172394A1 (en) * 2001-04-24 2002-11-21 Ramarathnam Venkatesan Robust and stealthy video watermarking
US7188249B2 (en) 2001-04-24 2007-03-06 Microsoft Corporation Derivation and quantization of robust non-local characteristics for blind watermarking
US7617398B2 (en) 2001-04-24 2009-11-10 Microsoft Corporation Derivation and quantization of robust non-local characteristics for blind watermarking
US20050022004A1 (en) * 2001-04-24 2005-01-27 Microsoft Corporation Robust recognizer of perceptually similar content
US20050066177A1 (en) * 2001-04-24 2005-03-24 Microsoft Corporation Content-recognition facilitator
US20050065974A1 (en) * 2001-04-24 2005-03-24 Microsoft Corporation Hash value computer of content of digital signals
US20050066176A1 (en) * 2001-04-24 2005-03-24 Microsoft Corporation Categorizer of content in digital signals
US20050094847A1 (en) * 2001-04-24 2005-05-05 Microsoft Corporation Robust and stealthy video watermarking into regions of successive frames
US20050108543A1 (en) * 2001-04-24 2005-05-19 Microsoft Corporation Derivation and quantization of robust non-local characteristics for blind watermarking
US20050108545A1 (en) * 2001-04-24 2005-05-19 Microsoft Corporation Derivation and quantization of robust non-local characteristics for blind watermarking
US20050105733A1 (en) * 2001-04-24 2005-05-19 Microsoft Corporation Derivation and quantization of robust non-local characteristics for blind watermarking
US7181622B2 (en) 2001-04-24 2007-02-20 Microsoft Corporation Derivation and quantization of robust non-local characteristics for blind watermarking
US7636849B2 (en) 2001-04-24 2009-12-22 Microsoft Corporation Derivation and quantization of robust non-local characteristics for blind watermarking
US20050125671A1 (en) * 2001-04-24 2005-06-09 Microsoft Corporation Derivation and quantization of robust non-local characteristics for blind watermarking
US7568103B2 (en) 2001-04-24 2009-07-28 Microsoft Corporation Derivation and quantization of robust non-local characteristics for blind watermarking
US7657752B2 (en) 2001-04-24 2010-02-02 Microsoft Corporation Digital signal watermaker
US20020172425A1 (en) * 2001-04-24 2002-11-21 Ramarathnam Venkatesan Recognizer of text-based work
US20050273617A1 (en) * 2001-04-24 2005-12-08 Microsoft Corporation Robust recognizer of perceptually similar content
US20060059356A1 (en) * 2001-04-24 2006-03-16 Microsoft Corporation Derivation and quantization of robust non-local characteristics for blind watermarking
US20060059354A1 (en) * 2001-04-24 2006-03-16 Microsoft Corporation Derivation and quantization of robust non-local characteristics for blind watermarking
US20060069919A1 (en) * 2001-04-24 2006-03-30 Microsoft Corporation Derivation and quantization of robust non-local characteristics for blind watermarking
US7707425B2 (en) 2001-04-24 2010-04-27 Microsoft Corporation Recognizer of content of digital signals
US7356188B2 (en) 2001-04-24 2008-04-08 Microsoft Corporation Recognizer of text-based work
US7072493B2 (en) 2001-04-24 2006-07-04 Microsoft Corporation Robust and stealthy video watermarking into regions of successive frames
US7318158B2 (en) 2001-04-24 2008-01-08 Microsoft Corporation Derivation and quantization of robust non-local characteristics for blind watermarking
US7318157B2 (en) 2001-04-24 2008-01-08 Microsoft Corporation Derivation and quantization of robust non-local characteristics for blind watermarking
US7634660B2 (en) 2001-04-24 2009-12-15 Microsoft Corporation Derivation and quantization of robust non-local characteristics for blind watermarking
US7266244B2 (en) 2001-04-24 2007-09-04 Microsoft Corporation Robust recognizer of perceptually similar content
US7188065B2 (en) 2001-04-24 2007-03-06 Microsoft Corporation Categorizer of content in digital signals
US7085398B2 (en) * 2002-01-11 2006-08-01 Thales Method and system to decode image watermarks
US20040001626A1 (en) * 2002-01-11 2004-01-01 Severine Baudry Method and system to decode image watermarks
US7295677B2 (en) * 2002-03-01 2007-11-13 Hewlett-Packard Development Company, L.P. Systems and methods for adding watermarks using network-based imaging techniques
US20030165253A1 (en) * 2002-03-01 2003-09-04 Simpson Shell Sterling Systems and methods for adding watermarks using network-based imaging techniques
US7095873B2 (en) 2002-06-28 2006-08-22 Microsoft Corporation Watermarking via quantization of statistics of overlapping regions
US7136535B2 (en) 2002-06-28 2006-11-14 Microsoft Corporation Content recognizer via probabilistic mirror distribution
US20040001605A1 (en) * 2002-06-28 2004-01-01 Ramarathnam Venkatesan Watermarking via quantization of statistics of overlapping regions
US20060167882A1 (en) * 2003-02-25 2006-07-27 Ali Aydar Digital rights management system architecture
US20060167804A1 (en) * 2003-02-25 2006-07-27 Ali Aydar Track listening and playing service for digital media files
US8180792B2 (en) 2003-02-25 2012-05-15 Myspace Music Llc Method of processing song claims involving songs including, but not limited to musical works, compositions, etc
US20060167807A1 (en) * 2003-02-25 2006-07-27 Ali Aydar Dispute resolution in an open copyright database
US8117130B2 (en) 2003-02-25 2012-02-14 Stragent, Llc Batch loading and self-registration of digital media files
US20060167813A1 (en) * 2003-02-25 2006-07-27 Ali Aydar Managing digital media rights through missing masters lists
US20060294371A1 (en) * 2003-02-25 2006-12-28 Shawn Fanning Content Regulation
US20060167803A1 (en) * 2003-02-25 2006-07-27 Ali Aydar Batch loading and self-registration of digital media files
US20060212403A1 (en) * 2003-02-25 2006-09-21 Shawn Fanning Method of processing song claims involving songs including, but not limited to musical works, compositions, etc.
US20040210539A1 (en) * 2003-04-21 2004-10-21 Yamaha Corporation Music-content using apparatus capable of managing copying of music content, and program therefor
US20130219521A1 (en) * 2003-04-21 2013-08-22 Yamaha Corporation Music-content using apparatus capable of managing copying of music content, and program therefor
US9836615B2 (en) * 2003-04-21 2017-12-05 Yamaha Corporation Music-content using apparatus capable of managing copying of music content, and program therefor
US20060116966A1 (en) * 2003-12-04 2006-06-01 Pedersen Palle M Methods and systems for verifying protectable content
US20080154965A1 (en) * 2003-12-04 2008-06-26 Pedersen Palle M Methods and systems for managing software development
US20050125358A1 (en) * 2003-12-04 2005-06-09 Black Duck Software, Inc. Authenticating licenses for legally-protectable content based on license profiles and content identifiers
US20050125359A1 (en) * 2003-12-04 2005-06-09 Black Duck Software, Inc. Resolving license dependencies for aggregations of legally-protectable content
US7552093B2 (en) 2003-12-04 2009-06-23 Black Duck Software, Inc. Resolving license dependencies for aggregations of legally-protectable content
US9489687B2 (en) 2003-12-04 2016-11-08 Black Duck Software, Inc. Methods and systems for managing software development
US8700533B2 (en) 2003-12-04 2014-04-15 Black Duck Software, Inc. Authenticating licenses for legally-protectable content based on license profiles and content identifiers
US20050149727A1 (en) * 2004-01-06 2005-07-07 Kozat S. S. Digital goods representation based upon matrix invariances
US7831832B2 (en) 2004-01-06 2010-11-09 Microsoft Corporation Digital goods representation based upon matrix invariances
US20050165690A1 (en) * 2004-01-23 2005-07-28 Microsoft Corporation Watermarking via quantization of rational statistics of regions
US20050175224A1 (en) * 2004-02-11 2005-08-11 Microsoft Corporation Desynchronized fingerprinting method and system for digital multimedia data
US7382905B2 (en) 2004-02-11 2008-06-03 Microsoft Corporation Desynchronized fingerprinting method and system for digital multimedia data
US7770014B2 (en) 2004-04-30 2010-08-03 Microsoft Corporation Randomized signal transforms and their applications
US8595276B2 (en) 2004-04-30 2013-11-26 Microsoft Corporation Randomized signal transforms and their applications
US20100228809A1 (en) * 2004-04-30 2010-09-09 Microsoft Corporation Randomized Signal Transforms and Their Applications
US8009859B2 (en) 2004-12-13 2011-08-30 Electronics And Telecommunications Research Institute Method and systems for selecting test stimuli for use in evaluating performance of video watermarking methods
US20080085054A1 (en) * 2004-12-13 2008-04-10 Electronics And Telecommunications Research Institute Method And Systems For Selecting Test Stimuli For Use In Evaluating Performance Of Video Watermarking Methods
WO2006065023A1 (en) * 2004-12-13 2006-06-22 Electronics And Telecommunications Research Institute Method and systems for selecting test stimuli for use in evaluating performance of video watermarking methods
US7797245B2 (en) 2005-03-18 2010-09-14 Black Duck Software, Inc. Methods and systems for identifying an area of interest in protectable content
US20060212464A1 (en) * 2005-03-18 2006-09-21 Pedersen Palle M Methods and systems for identifying an area of interest in protectable content
US8010538B2 (en) 2006-05-08 2011-08-30 Black Duck Software, Inc. Methods and systems for reporting regions of interest in content files
US20070260651A1 (en) * 2006-05-08 2007-11-08 Pedersen Palle M Methods and systems for reporting regions of interest in content files
US20070297014A1 (en) * 2006-06-23 2007-12-27 Takeshi Kuga Image processing system and image processing method
US20080091938A1 (en) * 2006-10-12 2008-04-17 Black Duck Software, Inc. Software algorithm identification
US8010803B2 (en) 2006-10-12 2011-08-30 Black Duck Software, Inc. Methods and apparatus for automated export compliance
US20080091677A1 (en) * 2006-10-12 2008-04-17 Black Duck Software, Inc. Software export compliance
US8650195B2 (en) 2010-03-26 2014-02-11 Palle M Pedersen Region based information retrieval system
US20110238664A1 (en) * 2010-03-26 2011-09-29 Pedersen Palle M Region Based Information Retrieval System
CN103810409A (zh) * 2012-11-02 2014-05-21 索尼公司 信息处理装置、信息处理方法和计算机程序
US20140130148A1 (en) * 2012-11-02 2014-05-08 Sony Corporation Information processing device, information processing method, and computer program
US9501633B2 (en) * 2012-11-02 2016-11-22 Sony Corporation Information processing device, information processing method, and computer program
CN103810409B (zh) * 2012-11-02 2018-01-19 索尼公司 信息处理装置、信息处理方法和计算机程序
WO2015099646A1 (en) * 2013-12-23 2015-07-02 Thomson Licensing Method and system for matching images and display devices
US10182170B1 (en) 2016-02-03 2019-01-15 Digimarc Corporation Methods and arrangements for adaptation of barcode reading camera systems for digital watermark decoding
US10735623B2 (en) 2016-02-03 2020-08-04 Digimarc Corporation Arrangements for enhancing digital watermark decoding
US11922263B2 (en) 2021-07-30 2024-03-05 Sick Ag Method of automatically setting up a code reading device and camera-based code reading device
EP4124991A1 (de) * 2021-07-30 2023-02-01 Sick Ag Verfahren zum automatischen einrichten einer codelesevorrichtung und kamerabasierte codelesevorrichtung

Similar Documents

Publication Publication Date Title
US6546114B1 (en) Technique for detecting a watermark in a marked image
US6574348B1 (en) Technique for watermarking an image and a resulting watermarked image
Brassil et al. Copyright protection for the electronic distribution of text documents
Rawat et al. A chaotic system based fragile watermarking scheme for image tamper detection
Celik et al. Hierarchical watermarking for secure image authentication with localization
Agrawal et al. Watermarking relational databases
US7577272B2 (en) Digital fingerprinting using synchronization marks and watermarks
Hwang et al. Digital watermarking of images using neural networks
US20050036651A1 (en) Digital anti&minus forging method
Hosam Attacking image watermarking and steganography-a survey
Nawaz et al. Advance hybrid medical watermarking algorithm using speeded up robust features and discrete cosine transform
Ghazvini et al. An improved image watermarking method in frequency domain
Kale et al. Data leakage detection
Amiri et al. Robust watermarking against print and scan attack through efficient modeling algorithm
Hamid et al. Robust image hashing scheme using Laplacian pyramids
Hatoum et al. Normalized blind STDM watermarking scheme for images and PDF documents robust against fixed gain attack
Hadmi et al. A robust and secure perceptual hashing system based on a quantization step analysis
Agreste et al. Wavelet-based watermarking algorithms: theory, applications and critical aspects
Nejati et al. Fragile watermarking based on QR decomposition and Fourier transform
Arya et al. A review on different digital watermarking techniques
WO2001018752A1 (en) A technique for watermarking an image and a resulting 'watermarked' image
Macit et al. Tamper detection and recovery on RGB images
Johnson et al. A role for digital watermarking in electronic commerce
Riaz et al. A robust multimedia authentication and restoration scheme in digital photography
Kashifa et al. Digital Image Watermarking and Its Applications: A Detailed Review

Legal Events

Date Code Title Description
AS Assignment

Owner name: MICROSOFT CORPORATION, WASHINGTON

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:VENKATESAN, RAMARATHNAM;JAKUBOWSKI, MARIUSZ;THATHACHAR, JAYRAM S.;REEL/FRAME:010236/0909;SIGNING DATES FROM 19990607 TO 19990701

CC Certificate of correction
FPAY Fee payment

Year of fee payment: 4

FPAY Fee payment

Year of fee payment: 8

REMI Maintenance fee reminder mailed
AS Assignment

Owner name: MICROSOFT TECHNOLOGY LICENSING, LLC, WASHINGTON

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:MICROSOFT CORPORATION;REEL/FRAME:034541/0001

Effective date: 20141014

LAPS Lapse for failure to pay maintenance fees
STCH Information on status: patent discontinuation

Free format text: PATENT EXPIRED DUE TO NONPAYMENT OF MAINTENANCE FEES UNDER 37 CFR 1.362

FP Lapsed due to failure to pay maintenance fee

Effective date: 20150408